Financial AI

The Financial AI theme at NaCTeM develops open language models, evaluation benchmarks and agent-based methods for the analysis of financial text and data.

Financial decision-making relies on large volumes of unstructured text, including regulatory filings, earnings call transcripts, news and analyst reports. Large language models offer new means of processing this material, yet their reliability in the financial domain is not well understood: numerical reasoning, specialised terminology and non-English markets remain persistent difficulties, and many systems cannot be independently examined.

The theme addresses these questions through three commitments: models and data that are openly released, evaluation that is rigorous and reproducible, and coverage of languages and markets beyond English. Much of this work is carried out in collaboration with The Fin AI, an open-source research community for financial AI.

Research areas

Open financial models. Open-FinLLMs, open multimodal language models for financial applications, and bilingual models and instruction data for Chinese–English and Spanish–English finance (KDD 2024).
Benchmarks and evaluation. FinBen, a holistic financial benchmark (NeurIPS 2024), and its multilingual, multimodal successor MultiFinBen; FinChain for verifiable step-by-step reasoning; FinAudio for financial speech; Plutus for low-resource Greek finance (EMNLP 2025); and cognitive diagnosis that reports skills, not just scores.
Agents for financial decisions. FLAG-Trader, which trains language-model trading agents with reinforcement learning (Findings of ACL 2025); a live multi-market trading benchmark for LLM agents; and retrieval-augmented forecasting of financial time series.
Financial misinformation. FMDLlama for detecting false or misleading financial claims (The Web Conference 2025), and shared tasks that open these problems to the community at FinNLP 2024 and 2025.

Projects

NVIDIA (current): multi-agent reinforcement learning that models how traders, institutions and AI systems interact in markets.
10BE5 (past): a Knowledge Transfer Partnership with 10BE5 Ltd that automates fact-checking and verification for companies listing securities on public markets.

Open resources

PIXIU and FinBen: open financial language models, instruction data and the FinBen evaluation suite.
Open FinLLM Leaderboard: public, continuously updated rankings of financial language models.
Greek Financial LLM Leaderboard: the Plutus benchmark for Greek finance.
Agent Market Arena: LLM trading agents competing live across markets.
FinSeer: retrieval-augmented forecasting of financial time series, with models and data.
All models and datasets: Hugging Face and GitHub.

To use our models or benchmarks, or to work with us, get in touch.

Research team

Theme lead

SA Professor Sophia Ananiadou Director, National Centre for Text Mining

Doctoral researchers

Associated members

Former members

Publications (16)

2025

Cao, Y., Li, H., Yu, Y., Reddy Javaji, S., He, Y., Huang, J., Zhu, Z., Xie, Q., Liu, X. -Y., Subbalakshmi, K., Qiu, M., Ananiadou, S. and Nie., J. -Y., FinAudio: A Benchmark for Audio Large Language Models in Financial Applications, in: arXiv, 2025 [URL]
Xie, Z., Orel, D., Thareja, R., Sahnan, D., Madmoun, H., Zhang, F., Banerjee, D., Georgiev, G., Peng, X., Qian, L., Huang, J., Su, J., Singh, A., Xing, R., Elbadry, R., Xu, C., Li, H., Koto, F., Koychev, I., Chakraborty, T., Wang, Y., Lahlou, S., Stoyanov, V., Ananiadou, S. and Nakov, P., FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning, in: arXiv, 2025 [DOI] [URL]
Liu, Z., Wang, K., Bao, Z., Zhang, X., Dong, J., Yang, K, Kabir, M., Giannouris, P., Xing, R., Park, S., Kim, J., Li, D., Xie, Q. and Ananiadou, S., FinNLP-FNP-LLMFinLegal-2025 Shared Task: Financial Misinformation Detection Challenge Task, in: Proceedings of the Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal), pages 271–276, 2025 [URL]
Xiong, G., Deng, Z., Wang, K., Cao, Y., Li, H., Yu, Y., Peng, X., Lin, M., Smith, K., Liu, X. -Y., Huang, J., Ananiadou, S. and Xie, Q., FLAG-Trader: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading, in: Findings of the Association for Computational Linguistics: ACL 2025, pages 13921–13934, 2025 [DOI] [URL]
Liu, Z., Zhang, X., Yang, K, Xie, Q., Huang, J. and Ananiadou, S., FMDLlama: Financial Misinformation Detection Based on Large Language Models, in: Proceedings of the ACM on Web Conference 2025, pages 1153–1157, 2025 [DOI] [URL]
Kuang, Z., Zhu, F., Jiang, M., Lai, Y., Wang, Zelin, Wang, Zhitong, Qiu, M., Huang, Jiajia, Peng, M., Xie, Q. and Ananiadou, S., From Scores to Skills: A Cognitive Diagnosis Framework for Evaluating Financial Large Language Models, in: arXiv, 2025 [DOI] [URL]
Peng, X., Qian, L., Wang, Y., Xiang, R., He, Y., Ren, Y., Jiang, M., Zhao, J., He, H., Han, Y., Feng, Y., Jiang, Y., Cao, Y., Li, H., Yu, Y., Wang, X., Gao, P., Lin, S., Wang, K., Yang, S., Zhao, Y., Liu, Z., Lu, P., Huang, J., Wang, S., Papadopoulos, T., Giannouris, P., Soufleri, E., Chen, N., Xiong, G., Deng, Z., Zhao, Y., Lin, M., Qiu, M., Smith, K., Cohan, A., Liu, X. -Y., Lopez-Lira, A., Chen, X., Tsujii, J., Nie, J., Ananiadou, S. and Xie, Q., MultiFinBen: A Multilingual, Multimodal, and Difficulty-Aware Benchmark for Financial LLM Evaluation, in: arXiv, 2025 [URL]
Peng, X., Papadopoulos, T., Soufleri, E., Giannouris, P., Xiang, R., Wang, Y., Qian, L., Huang, J., Xie, Q. and Ananiadou, S., Plutus: Benchmarking Large Language Models in Low-Resource Greek Finance, in: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 30176–30202, 2025 [DOI] [URL]
Xiao, M., Jiang, Z., Qian, L., Chen, Z., He, Y., Xu, Y., Jiang, Y., Li, D., Weng, R. -L., Peng, M., Huang, J., Ananiadou, S. and Xie, Q., Retrieval-augmented Large Language Models for Financial Time Series Forecasting, in: arXiv, 2025 [URL]
Qian, L., Peng, X., Wang, Y., Zhang, V. J., He, H., Smith, H., Han, Y., He, Y., Li, H., Cao, Y., Yu, Y., Lopez-Lira, A., Lu, P., Nie., J. -Y., Xiong, G., Huang, J. and Ananiadou, S., When Agents Trade: Live Multi-Market Trading Benchmark for LLM Agents, in: arXiv, 2025 [DOI] [URL]

2024

Zhang, X., Xiang, R., Yuan, C., Feng, D., Han, W., Lopez-Lira, A., Liu, X. -Y., Ananiadou, S., Peng, M., Huang, J. and Xie, Q., Dólares or Dollars? Unraveling the Bilingual Prowess of Financial LLMs Between Spanish and English, in: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '24), pages 6236-6246, 2024 [DOI] [URL]
Xie, Q., Han, W., Chen, Z., Xiang, R., Zhang, X., He, Y., Xiao, M., Li, D., Dai, Y., Feng, D., Xu, Y., Kang, H., Kuang, Z., Yuan, C., Yang, K, Luo, Z., Zhang, T., Liu, Z., Xiong, G., Deng, Z., Jiang, Y., Yao, Z., Li, H., Yu, Y., Lopez-Lira, A., Wang, B., Lai, Y., Wang, H., Peng, M., Ananiadou, S. and Huang, J., FinBen: An Holistic Financial Benchmark for Large Language Models, in: Proceedings of the Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024 [URL]
Xie, Q., Huang, J., Li, D., Chen, Z., Xiang, R., Xiao, M., Yu, Y., Somasundaram, V., Yang, K, Yuan, C., Luo, Z., Liu, Z., He, Y., Jiang, Y., Li, H., Feng, D., Liu, X. -Y., Wang, B., Wang, H., Lai, Y., Suchow, J., Lopez-Lira, A., Peng, M. and Ananiadou, S., FinNLP-AgentScen-2024 Shared Task: Financial Challenges in Large Language Models - FinLLMs, in: Proceedings of the Eighth Financial Technology and Natural Language Processing and the 1st Agent AI for Scenario Planning, pages 119- 126, 2024 [URL]
Liu, Z., Zhang, X., Yang, K, Xie, Q., Huang, J. and Ananiadou, S., FMDLlama: Financial Misinformation Detection based on Large Language Models, in: arXiv, 2024 [URL]
Hu, G., Qin, K., Yuan, C., Peng, M., Lopez-Lira, A., Wang, B., Ananiadou, S., Huang, J. and Xie, Q., No Language is an Island: Unifying Chinese and English in Financial Large Language Models, Instruction Data, and Benchmarks, in: arXiv, 2024 [URL]
Xie, Q., Li, D., Xiao, M., Jiang, Y., Xiang, R., Zhang, X., Chen, Z., He, Y., Han, W., Yang, Y., Chen, S., Zhang, Y., Shen, L., Kim, D., Liu, Z., Luo, Z., Yu, Y., Cao, Y., Deng, Z., Yao, Z., Li, H., Feng, D., Dai, Y., Somasundaram, V., Lu, P., Zhao, Y., Long, Y., Xiong, G., Smith, K., Yu, H., Lai, Y., Peng, M., Nie, J., Suchow, J., Liu, X. -Y., Wang, B., Lopez-Lira, A., Huang, J. and Ananiadou, S., Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications, in: arXiv, 2024 [URL]

All NaCTeM publications →